Selected Topics in Intelligent Chips with Emerging Devices, Circuits and Systems

Description

Memristors have provided a new direction of thinking for circuit designers to overcome the limits of scalability and for thinking of building systems beyond Moore’s law. Over the last decade, there has been a significant number of innovations in using memristors for building neural networks through analog computing, in-memory computing, and stochastic computing approaches. The emergence of intelligent integrated circuits is inevitable for the future of integrated circuit applications. This book provides a collection of talks conducted as part of the IEEE Seasonal School on Circuits and System, having a focus on Intelligence in Chip: Tomorrow of Integrated Circuits. Technical topics discussed in the book include Edge of Chaos Theory Explains Complex Phenomena in Memristor Circuits Analog Memristive Computing Designing energy efficient neo-cortex system with on-device learning Integrated sensors Challenges and recent advances in NVM based Neuromorphic Computing ICs In-memory Computing (for deep learning) Deep learning with Spiking Neural Networks Computational Intelligence for Designing Integrated Circuits and Systems Neurochip Design, Modeling, and Applications Cover Title Page Series Page Copyright Page Table of Contents Introduction Chapter 1: Edge of Chaos Theory Explains Complex Phenomena in Memristor Circuits Chapter 2: Analog Memristive Computing Chapter 3: Designing Energy Efficient Neocortex-Inspired Systems with On-device Learning Chapter 4: Integrated Sensors Chapter 5: Challenges and Recent Advances in NVM-based Neuromorphic Computing ICs Chapter 6: In-memory Computing (for Deep Learning) Chapter 7: Deep Learning with Spiking Neural Nets Chapter 8: Computational Intelligence for Designing Integrated Circuits and Systems Chapter 9: Neurochip Design, Modeling, and Applications Appendix About the Editors About the Authors